Information processing device, information processing method, and program
The information processing device quantitatively evaluates equipment deterioration by analyzing operation data and updating thresholds, addressing performance degradation and enabling efficient maintenance and insurance processes.
Patent Information
- Application Number
- JP2023075841
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-01
- Publication Date
- 2024-11-14
- Estimated Expiration
- 2043-05-01
AI Technical Summary
Existing equipment designed to reduce carbon emissions gradually deteriorates, losing its original performance over time, necessitating a method to quantitatively evaluate the extent of deterioration.
An information processing device that acquires equipment operation data, determines an abnormality threshold, and calculates the degree of deterioration based on the difference between the threshold and operating state values, using probability density distributions and Bayesian updating to adapt to changes in equipment condition.
Enables quantitative assessment of equipment deterioration, facilitating timely maintenance and insurance claims, and ensuring accurate determination of equipment performance without frequent recalibration.
Smart Images

Figure 2024160626000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]
[0002] At present, efforts to achieve carbon neutrality are gaining momentum. For example, Patent Document 1 discloses an electric furnace that uses electricity that does not emit carbon dioxide and is generated from non-fossil fuel sources such as renewable energy sources in order to achieve decarbonization of the power sector. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2023-007360 A Summary of the Invention [Problem to be solved by the invention]
[0004] To achieve carbon neutrality, the amount of carbon dioxide emitted can be reduced by using equipment designed to emit as little carbon dioxide as possible. However, since the installed equipment gradually deteriorates, it is thought that it will no longer be able to perform at its initial level over time. Therefore, a mechanism that can quantitatively evaluate the degree of deterioration of equipment is desired. Note that this issue is not limited to equipment intended for deoxidation, but can occur in any type of equipment.
[0005] Therefore, an object of the present invention is to provide a technique that makes it possible to quantitatively grasp the degree of deterioration of equipment. [Means for solving the problem]
[0006] An information processing device according to one embodiment of the present invention has an acquisition unit that acquires equipment operation data indicating time-series changes in an operation state value of equipment, an extraction unit that extracts from the equipment operation data an abnormality occurrence period in which the operation state value is less than an abnormality threshold value during an evaluation period, and a calculation unit that calculates a degree of deterioration of the equipment based on a difference value between the abnormality threshold value and the operation state value during the abnormality occurrence period. Effect of the Invention
[0007] According to the present invention, it is possible to provide a technique that makes it possible to quantitatively grasp the degree of deterioration of equipment. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a management system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram for explaining an example of equipment operation data of equipment. [Diagram 3] FIG. 11 is a diagram illustrating an example of a method for determining an abnormality threshold value. [Figure 4] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device. [Diagram 5] FIG. 2 is a diagram illustrating an example of a functional block configuration of an information processing device. [Figure 6] 11 is a flowchart illustrating an example of a processing procedure in which the information processing device determines and updates an abnormality threshold value. [Figure 7] 11 is a flowchart illustrating an example of a processing procedure for an information processing device to calculate a deterioration degree of equipment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described with reference to the accompanying drawings, in which the same reference numerals denote the same or similar configurations.
[0010] <System configuration> 1 is a diagram showing an example of a management system 1 according to the present embodiment. The management system 1 includes an information processing device 10 and one or more facilities 20. The information processing device 10 and the facilities 20 may be connected via a wireless or wired communication network and may be capable of communicating with each other.
[0011] The information processing device 10 is a device that manages the operating state of the facility 20. The facility 20 is a mechanical facility that exerts some capability by operating, and does not include facilities that do not operate, such as land and buildings. Examples of the facility 20 include devices and equipment that contribute to the realization of a carbon-free society and the realization of carbon neutrality. Specifically, solar power generation equipment, boilers that use LNG (Liquefied Natural Gas), biomass fuel production equipment, etc. can be mentioned. The solar power generation equipment can generate electricity without emitting carbon dioxide. The LNG boiler can reduce carbon dioxide emissions compared to boilers that use heavy oil, etc. The biomass fuel production equipment can contribute to the realization of carbon neutrality by promoting the use of biomass fuel by producing biomass fuel.
[0012] The facility 20 according to the present embodiment is not necessarily limited to devices and equipment that contribute to the realization of a carbon-free society and carbon neutrality. The facility 20 may be any facility 20 as long as the operating state of the facility 20 can be expressed numerically.
[0013] The operation state of the equipment 20 means a state in which the equipment 20 is operating and exerting a predetermined capacity. In this embodiment, the operation state of the equipment 20 is expressed by a numerical value. In this embodiment, a value indicating the capacity exerted by the equipment 20 is called an "operation state value". The operation state value may be expressed as a percentage, with the maximum capacity that the equipment 20 can exert being 100%. Also, it is not limited to a percentage, and may be expressed as an absolute value. For example, in the case of a solar power generation equipment, the operation state value may be expressed by the amount of power generation (e.g., W), or may be expressed as a ratio of the amount of power generation at a certain time to the maximum power generation capacity (e.g., 30%). Also, in the case of a biomass fuel production device, the operation state value may be expressed by the amount of production at a certain time (e.g., X kg / day), or may be expressed as a ratio of the amount of production at a certain time to the maximum production capacity (e.g., 90%).
[0014] FIG. 2 is a diagram for explaining an example of equipment operation data of the equipment 20. The equipment operation data is data that represents a time series change in an operation state value. The vertical axis of the graph shown in FIG. 2A represents an operation state value (percentage in the example of FIG. 2), and the horizontal axis represents time. The equipment operation data may be composed of a large number of samples (one sample is a pair of an operation state value and a timestamp). The period from t4 to t5 indicates a period during which the equipment 20 was intentionally stopped due to equipment inspection or the like. Information representing the period during which the equipment 20 was intentionally stopped may be input to the information processing device 10 by, for example, a manager of the equipment 20.
[0015] Here, the abnormality threshold is a threshold for determining that the operation state value of the equipment 20 is abnormal. In this embodiment, when the operation state value is less than the abnormality threshold, it is determined that an abnormality has occurred in the equipment 20. On the other hand, when the operation state value is equal to or greater than the abnormality threshold, it is determined that the equipment 20 is normal. The abnormality threshold may be determined in advance by an administrator or the like, or may be determined by a predetermined determination method. The method of determining the abnormality threshold will be described later. In the period t1 to t3 in the equipment operation data, the operation state value is less than the abnormality threshold. In other words, the period t1 to t3 in the equipment operation data indicates that some abnormality has occurred in the equipment 20.
[0016] The probability density function f(x) shown in FIG. 2B indicates a probability density distribution of operation state values in a predetermined period (e.g., from one month ago to the present) excluding periods during which the equipment 20 was intentionally stopped. The shape of the probability density function f(x) differs depending on the equipment 20. For example, if the equipment 20 is always operating at full capacity, the operation state value always indicates a value close to 100%, so the shape of the probability density function f(x) is expected to be as shown in FIG. 2B. On the other hand, if the equipment 20 operates at about 50% on average but increases or decreases the operation amount depending on the season, the shape of the probability density function f(x) is expected to be close to a normal distribution. The probability density distribution may be obtained, for example, by counting the number of samples included in the equipment operation data for each operation state value to create a histogram and graphing the created histogram.
[0017] Furthermore, in this embodiment, when the operation state value is less than the abnormality threshold, the value obtained by subtracting the operation state value from the abnormality threshold is called the "degree of abnormality." In other words, the degree of abnormality (t) at time t can be calculated by the formula: degree of abnormality (t) = abnormality threshold - operation state value (t). The magnitude of the degree of abnormality shown in A of FIG. 2 indicates the degree of abnormality at time (t2). Since the degree of abnormality is the value obtained by subtracting the operation state value from the abnormality threshold, the larger the value, the greater the degree of abnormality that has occurred in the equipment 20.
[0018] FIG. 3 is a diagram showing an example of a method for determining the abnormality threshold. For example, the abnormality threshold may be a predetermined value when a cumulative probability (i.e., upper probability) obtained by integrating the operation state value x from a predetermined value to a maximum value with respect to a probability density function f(x) of the operation state value becomes a predetermined probability. For example, in the example of FIG. 3, an operation state value x1 is determined as the abnormality threshold when a cumulative probability obtained by integrating the operation state value from a predetermined value to a maximum value becomes 95% (i.e., when the area of the right part inside the graph in FIG. 3 becomes 95%). Note that the predetermined probability is not limited to 95%. For example, it may be 80% or 99%.
[0019] In this embodiment, the integral of the abnormal value for the period during which the operation state value is less than the abnormal threshold value during the period during which the deterioration of the equipment 20 is evaluated (hereinafter referred to as the "evaluation period") is defined as the "degree of deterioration of the equipment." Specifically, the degree of deterioration of the equipment can be calculated by the following formula (1).
number
[0020] For example, when it is desired to evaluate the deterioration of the equipment 20 in the past year (i.e., when the evaluation target period is the past year), the "degree of deterioration of the equipment" in the past year can be calculated by integrating the abnormal value for the period from one year ago to the present when the operation state value was less than the abnormal threshold. Also, when it is desired to evaluate the deterioration of the equipment 20 in the period from two years ago to one year ago (i.e., when the evaluation target period is from two years ago to one year ago), the "degree of deterioration of the equipment" in the period from two years ago to one year ago can be calculated by integrating the abnormal value for the period from two years ago to one year ago when the operation state value was less than the abnormal threshold. In this way, by comparing the "degree of deterioration of the equipment" in different evaluation target periods, it is possible to grasp the extent to which the deterioration of the equipment 20 has progressed. Also, by using machine learning technology to analyze the tendency of change in the "degree of deterioration of the equipment" for multiple evaluation target periods, it is also possible to estimate the "degree of deterioration of the equipment" in the future.
[0021] The information processing device 10 may also have a function for calculating insurance money. As an example of insurance for which the information processing device 10 calculates insurance money, for example, insurance that insures against deterioration of the facility 20 is considered. For example, the information processing device 10 may calculate the amount of insurance money to be paid to the insured person based on the degree of deterioration of the facility. Normally, in non-life insurance, deterioration of the facility 20 is clearly stated as an exemption from liability, and therefore is not subject to insurance money payment. However, according to the present embodiment, since the degree of deterioration of the facility 20 can be calculated, it is possible to provide insurance that covers deterioration of the facility 20.
[0022] <Hardware configuration> 4 is a diagram showing an example of a hardware configuration of the information processing device 10. The information processing device 10 has a processor 11 such as a CPU (Central Processing Unit) or a GPU (Graphical Processing Unit), a memory (e.g., RAM or ROM), a storage device 12 such as an HDD (Hard Disk Drive) and / or an SSD (Solid State Drive), a network IF (Network Interface) 13 for wired or wireless communication, an input device 14 for accepting input operations, and an output device 15 for outputting information. The input device 14 is, for example, a keyboard, a touch panel, a mouse, and / or a microphone. The output device 15 is, for example, a display, a touch panel, and / or a speaker.
[0023] The information processing device 10 may be configured with one or more physical servers, may be configured using a virtual server operating on a hypervisor, or may be configured using a cloud server.
[0024] <Function block configuration> FIG. 5 is a diagram showing an example of a functional block configuration of the information processing device 10. The information processing device 10 includes a storage unit 100, an acquisition unit 101, an extraction unit 102, a calculation unit 103, a determination unit 104, and an insurance payment calculation unit 105. The storage unit 100 can be realized by using a storage device 12 included in the information processing device 10. The acquisition unit 101, the extraction unit 102, the calculation unit 103, the determination unit 104, and the insurance payment calculation unit 105 can be realized by the processor 11 of the information processing device 10 executing a program stored in the storage device 12. The storage unit 100 can be realized by the storage device 12. The program can be stored in a storage medium. The storage medium storing the program may be a non-transitory computer readable medium. The non-transitory storage medium is not particularly limited, and may be, for example, a storage medium such as a Universal Serial Bus (USB) memory or a Compact Disc Read-Only Memory (CD-ROM).
[0025] The storage unit 100 stores an equipment operation DB (Data Base) 100a. The equipment operation DB 100a is a database that stores equipment operation data for each equipment 20.
[0026] The acquiring unit 101 acquires equipment operation data indicating time-series changes in the operation state value of the equipment 20 from the equipment operation DB 100a.
[0027] The extraction unit 102 extracts a period (abnormality occurrence period) during which the operation state value is less than the abnormality threshold during the evaluation period from the equipment operation data acquired by the acquisition unit 101. For example, when extracting an abnormality occurrence period from the equipment operation data shown in A of Fig. 2, the extraction unit 102 extracts a period from t1 to t3 as the abnormality occurrence period.
[0028] The calculation unit 103 calculates the degree of deterioration of the equipment based on the difference value (i.e., the degree of abnormality) between the abnormality threshold value and the operating state value during the abnormality occurrence period.
[0029] Furthermore, the calculation unit 103 generates a probability density distribution (probability density) of the operation state values from the equipment operation data for a predetermined period.
[0030] The determining unit 104 determines, as the abnormality threshold, a predetermined value at which a cumulative probability obtained by integrating the operation state value from a predetermined value to a maximum value becomes a predetermined probability for the probability density distribution calculated by the calculating unit 103. The determining unit 104 may also update the abnormality threshold by using equipment operation data for a predetermined period after updating.
[0031] The insurance payment calculation unit 105 calculates the amount of insurance payment based on the degree of deterioration of the equipment.
[0032] <Processing Procedure> (Determination of abnormality threshold) FIG. 6 is a flowchart showing an example of a processing procedure in which the information processing device 10 determines and updates the abnormality threshold value.
[0033] In step S100, the acquisition unit 101 accesses the equipment operation DB 100a and acquires equipment operation data of the equipment 20 for a predetermined period. The predetermined period may be any length as long as it is set within the period from the past to the present. The predetermined period may be set according to the deterioration rate of the equipment 20. For example, for equipment 20 that is subject to rapid deterioration due to operation under high load, it is preferable to update the abnormality threshold value frequently. Therefore, the predetermined period may be set to a short period (e.g., the past month or the past week). On the other hand, for equipment 20 that is not subject to significant deterioration, it is considered that there is little need to update the abnormality threshold value frequently. Therefore, the predetermined period may be set to a long period (e.g., the past six months or the past year).
[0034] In step S101, the calculation unit 103 generates a probability density distribution from the equipment operation data acquired in step S100, the equipment operation data being for a period excluding a period during which the equipment 20 was intentionally stopped. Generating a probability density distribution is synonymous with obtaining a probability density function f(x). The probability density distribution may be generated, for example, by using an existing library or the like. Also, as described above, the probability density distribution may be generated by counting the number of samples included in the equipment operation data for each operation state value.
[0035] In step S102, the determination unit 104 determines, as the abnormality threshold, the operating state value when the upper probability of the probability density distribution calculated in step S101 becomes a predetermined probability. The predetermined probability is arbitrary, but it may be set to, for example, 80%, 95%, 99%, etc. The predetermined probability may be determined according to the type of the equipment 20, etc.
[0036] If the probability density distribution can be approximated by a normal distribution, the determination unit 104 may determine the abnormality threshold value using the Mahalanobis distance. Specifically, the operating state value corresponding to a position where the Mahalanobis distance in the probability density distribution is a predetermined negative value (for example, −1.96 corresponding to an upper probability of 95%) may be set as the abnormality threshold value.
[0037] (Update of abnormality threshold) Next, a processing procedure when the information processing device 10 updates the abnormality threshold will be described. The equipment 20 may undergo improvement of processing capacity through maintenance or the like, may be replaced with a new device through equipment renewal, or may undergo equipment expansion or the like to improve processing capacity. In such cases, if an abnormality threshold based on a probability density distribution calculated in the past is used, it may be difficult to correctly determine an abnormality in the equipment 20. Therefore, the information processing device 10 updates the probability density distribution and updates the abnormality threshold using the updated probability density distribution.
[0038] The update of the probability density distribution and the abnormality threshold may be performed by repeating the process procedure shown in Fig. 6 at a predetermined cycle. That is, the acquisition unit 101 of the information processing device 10 may access the equipment operation DB 100a again in the process procedure of step S100 to acquire equipment operation data of the equipment 20 for a predetermined period (i.e., updated equipment operation data). Furthermore, the calculation unit 103 may update the probability density distribution using the updated equipment operation data in the process procedure of step S101. Furthermore, the determination unit 104 may update the abnormality threshold based on the updated probability density in the process procedure of step S102.
[0039] For example, the information processing device 10 may initially determine the abnormality threshold value using equipment operation data from "January 1st to January 31st." In this case, the information processing device 10 may update the abnormality threshold value one month later by performing a process of determining the abnormality threshold value using equipment operation data from "February 1st to February 28th." Thereafter, the information processing device 10 may repeatedly update the abnormality threshold value by repeating a process of determining the abnormality threshold value using equipment operation data from the most recent month every month. As a result, even if equipment renewal is performed in April, for example, the information processing device 10 can determine the abnormality threshold value using equipment operation data from "May 1st to May 31st" in June, thereby updating the abnormality threshold value to a value that reflects the state of the equipment 20 after the equipment renewal.
[0040] Note that the information processing device 10 may update the probability density distribution using Bayesian updating in the processing procedures of steps S100 and S101. Equation (2) is a general equation expressing Bayesian updating.
number
[0041] If the probability density distribution is a normal distribution, the calculation unit 103 may calculate the mean and variance of the updated probability density distribution by the following formulas (3) and (4), respectively.
number
number
[0042] (Calculation of the degree of deterioration of equipment) FIG. 7 is a flowchart showing an example of a processing procedure for the information processing device 10 to calculate the deterioration degree of the facility.
[0043] In step S200, the calculation unit 103 determines whether or not there is a period (abnormality occurrence period) in which the operating state value is less than the abnormality threshold value in the evaluation period. If there is no abnormality occurrence period, the process ends, and if there is, the process proceeds to step S201.
[0044] In step S201, the calculation unit 103 calculates the deterioration degree of the equipment based on the degree of abnormality in the abnormality occurrence period. More specifically, the calculation unit 103 calculates a value obtained by integrating the time series change in the degree of abnormality in the abnormality occurrence period over the abnormality occurrence period as the deterioration degree of the equipment.
[0045] For example, assume that the evaluation period is "January 1st to January 31st." Also assume that the operation status value was below the abnormality threshold value between 10:00 and 11:00 on January 5th and between 8:00 and 10:00 on January 20th. In this case, the calculation unit 103 determines the degree of deterioration of the equipment to be the sum of the value obtained by integrating the abnormality degree (t) between 10:00 and 11:00 on January 5th and the value obtained by integrating the abnormality degree (t) between 8:00 and 10:00 on January 20th.
[0046] <Calculation of insurance benefits> The insurance payment calculation unit 105 calculates the insurance payment amount based on the degree of deterioration of the facility. For example, the insurance payment calculation unit 105 may calculate the insurance payment amount for insurance that compensates for the deterioration of the facility 20 based on the following formula (5). Insurance payment amount = Degree of deterioration of equipment × Coefficient (5) The coefficient may be a value determined in advance based on, for example, the type, model, and installation date of the equipment 20.
[0047] The insurance payment calculation unit 105 may calculate the amount of insurance payment for insurance compensating for a breakdown of the equipment 20 based on the following formula (6). The values of the "equipment manufacturer's published performance" and the "degree of deterioration of the equipment" substituted into formula (6) may be normalized values. By using formula (6), the insurance payment amount decreases as the equipment 20 deteriorates. Insurance payment amount = ("Facility manufacturer's published performance" - "Degree of deterioration of facility") x coefficient (6)
[0048] <Summary> According to the embodiment described above, the information processing device 10 defines the integrated value of the operation state values less than the abnormality threshold value among the operation state values during the evaluation period as the deterioration degree of the equipment. This makes it possible to quantitatively grasp the gradually progressing deterioration degree of the equipment 20.
[0049] Furthermore, the information processing device 10 uses an abnormality threshold value to identify whether the operation state of the equipment 20 is abnormal or not. Usually, while the equipment 20 is operating, the operation state value is not constant, and a certain degree of fluctuation (fluctuation) generally occurs. In this embodiment, the equipment 20 is determined to be operating normally unless the operation state of the equipment 20 falls below the abnormality threshold value, thereby making it possible to prevent the equipment 20 from erroneously determining that the operation state is abnormal when the equipment 20 is operating normally.
[0050] Furthermore, the information processing device 10 uses the latest newly collected equipment operation data to update the probability density distribution of the operation state value of the equipment 20, and updates the abnormality threshold value based on the updated probability density distribution. The equipment 20 may undergo improvement of processing capacity through maintenance or the like, may be replaced with a new device through equipment renovation, or may undergo equipment expansion or the like to improve processing capacity. Even in such cases, it becomes possible to update the abnormality threshold value to a more appropriate value.
[0051] Conventional insurance products require a lot of time to pay insurance money because the insurance company must first check whether there is an equipment failure or accident before deciding whether to pay insurance money and the amount of insurance money to be paid. On the other hand, when considering insurance as an example of an embodiment of the present invention, it becomes possible to determine the amount of insurance money to be paid for abnormal deterioration according to the degree of deterioration of the equipment. Therefore, there is less need to check whether there is an equipment failure or accident than before, and it becomes possible to quickly determine the amount of insurance money to be paid.
[0052] The above-described embodiments are intended to facilitate understanding of the present invention, and are not intended to limit the present invention. The flow charts, sequences, elements included in the embodiments, and their arrangements, materials, conditions, shapes, sizes, etc. are not limited to those illustrated, and can be changed as appropriate. In addition, configurations shown in different embodiments can be partially replaced or combined with each other. [Explanation of symbols]
[0053] 1 Management system, 10 Information processing device, 11 Processor, 12 Storage device, 13 Network IF (Network Interface), 14 Input device, 15 Output device, 20 Equipment, 101 Acquisition unit, 102 Extraction unit, 103 Calculation unit, 104 Determination unit, 105 Insurance payment calculation unit
Claims
1. An acquisition unit that acquires equipment operation data indicating time-series changes in an operation state value of the equipment; an extraction unit that extracts, from the equipment operation data, an abnormality occurrence period during which the operation state value is less than an abnormality threshold value during an evaluation period; a calculation unit that calculates a deterioration degree of the equipment based on a difference value between the abnormality threshold value and the operating state value during the abnormality occurrence period; An information processing device having the above configuration.
2. The calculation unit calculates a probability density of the operation state value from the equipment operation data for a predetermined period of time, a determination unit that determines, as the abnormality threshold, a predetermined value at which a cumulative probability obtained by integrating the operation state value from a predetermined value to a maximum value for the probability density becomes a predetermined probability, The information processing device according to claim 1 .
3. the determination unit updates the abnormality threshold value by using the equipment operation data for the predetermined period after updating. The information processing device according to claim 2 .
4. The calculation unit calculates a value obtained by integrating a time series change in the difference value during the abnormality occurrence period over the abnormality occurrence period as a deterioration degree of the equipment. The information processing device according to claim 1 .
5. An insurance payment calculation unit that calculates an insurance payment amount based on a deterioration degree of the equipment. The information processing device according to claim 1 .
6. acquiring equipment operation data indicating time-series changes in an operation status value of the equipment; extracting, from the equipment operation data, an abnormality occurrence period during which the operation state value is less than an abnormality threshold value during an evaluation period; calculating a degree of deterioration of the equipment based on a difference value between the abnormality threshold value and the operating state value during the abnormality occurrence period; An information processing method comprising:
7. acquiring equipment operation data indicating time-series changes in an operation status value of the equipment; extracting, from the equipment operation data, an abnormality occurrence period during which the operation state value is less than an abnormality threshold value during an evaluation period; calculating a degree of deterioration of the equipment based on a difference value between the abnormality threshold value and the operating state value during the abnormality occurrence period; A program for causing a computer to execute the following.
Citation Information
Patent Citations
Equipment maintenance method and device, electronic equipment and storage medium
CN115470946A
Damage compensating device, damage compensating method, computer program and compensation system for abnormality of power transmission
JP2007141016A
Information processing apparatus, information processing method, and program
JP2020057089A
Information presentation device, information presentation method, and information presentation system
JP2021043764A
Information processing method, program, information processing device, and information processing system
JP2021179693A
